Model Context Protocol server for desktop automation
Model Context Protocol server for desktop automation
A Model Context Protocol server that provides desktop automation capabilities using RobotJS and screenshot capabilities. This server enables LLMs to control mouse movements, keyboard inputs, and capture screenshots of the desktop environment.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_screen_size | Gets the screen dimensions |
| screen_capture | Captures the current screen content |
| keyboard_press | Presses a keyboard key or key combination |
| Inputs: | x (number, required): X coordinate |
| modifiers | array of strings, optional): Modifier keys to hold while pressing the key. Possible values: "control", "shift", "alt", "command" |
| keyboard_type | Types text at the current cursor position |
| mouse_click | Performs a mouse click |
| double | boolean, optional, default: false): Whether to perform a double click |
| mouse_move | Moves the mouse to specified coordinates |
{
"mcpServers": {
"desktop-automation": {
"command": "npx",
"args": [
"-y",
"mcp-desktop-automation"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Local always-on server for SnapStack: browser capture intake + MCP over 127.0.0.1.
Parse a User-Agent: browser, OS, device, plus bot, search crawler, AI crawler and AI agent flags.
220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.
Lets Claude Code or Codex CLI drive your real Chrome — sessions intact, 26 browser tools.